Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Comprehensive Survey on Source-Free Domain Adaptation
Jingjing Li, Zhiqi Yu, Zhekai Du, Lei Zhu, Heng Tao Shen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| upgrade SHOT to SHOT++ (pseudo-labeling plus entropy minimization, refined) | SHOT · Office-31 | Avg. accuracy (%): 88.6 -> 89.2 | Improved |
| add contrastive learning to pseudo-labeling (HCL+SHOT) | SHOT · Office-31 | Avg. accuracy (%): 88.6 -> 89.8 | Improved |
| add virtual domain generation and pseudo-labeling on top of SHOT++ (Kundu et al.) | SHOT++ · Office-31 | Avg. accuracy (%): 89.2 -> 90.7 | Improved |
| add BMD class-balanced pseudo-label refinement to SHOT++ | SHOT++ · Office-31 | Avg. accuracy (%): 89.2 -> 90.1 | Improved |
| add self-attention (transformer) to pseudo-labeling (TransDA) | pseudo-labeling SFDA · Office-31 | Avg. accuracy (%): 88.6 -> 90.7 | Improved |
| use source-free adaptation instead of target-supervised oracle | best SFDA method · Office-31 | Avg. accuracy (%): 3.6% lower than target supervision | Hurt |
| use source-free adaptation instead of target-supervised oracle | TransDA · Office-Home | Avg. accuracy (%): 2.7% lower than target supervision | Hurt |
| use source-free adaptation instead of target-supervised oracle | BMD + SHOT++ · VisDA-C | Avg. accuracy (%): 0.9% lower than target supervision | Hurt |
| adapt with SFDA instead of source-only model | SHOT · Office-31 | Avg. accuracy (%): 76.1 -> 88.6 | Improved |
Closest papers by meaning
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.94)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.93)
- Generalized Source-Free Domain Adaptation (ICCV 2021 · similarity 0.92)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.91)
- Dynamic Target Distribution Estimation for Source-Free Open-Set Domain Adaptation (AAAI 2025 · similarity 0.89)
- Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
